Re: [arp222] New Non-WG Mailing List: arp222@ietf.org

Linda Dunbar <ldunbar@huawei.com> Thu, 22 July 2010 04:03 UTC

Return-Path: <ldunbar@huawei.com>
X-Original-To: arp222@core3.amsl.com
Delivered-To: arp222@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 8F91A3A6902 for <arp222@core3.amsl.com>; Wed, 21 Jul 2010 21:03:48 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.599
X-Spam-Level:
X-Spam-Status: No, score=-2.599 tagged_above=-999 required=5 tests=[BAYES_00=-2.599]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id b19efiFHpHMA for <arp222@core3.amsl.com>; Wed, 21 Jul 2010 21:03:47 -0700 (PDT)
Received: from usaga01-in.huawei.com (usaga01-in.huawei.com [206.16.17.211]) by core3.amsl.com (Postfix) with ESMTP id 8A73D3A68A5 for <arp222@ietf.org>; Wed, 21 Jul 2010 21:03:47 -0700 (PDT)
Received: from huawei.com (usaga01-in [172.18.4.6]) by usaga01-in.huawei.com (iPlanet Messaging Server 5.2 HotFix 2.14 (built Aug 8 2006)) with ESMTP id <0L5X006R5XYRGN@usaga01-in.huawei.com> for arp222@ietf.org; Wed, 21 Jul 2010 21:04:03 -0700 (PDT)
Received: from L735042 ([206.191.100.2]) by usaga01-in.huawei.com (iPlanet Messaging Server 5.2 HotFix 2.14 (built Aug 8 2006)) with ESMTPA id <0L5X00GHHXYQ3X@usaga01-in.huawei.com> for arp222@ietf.org; Wed, 21 Jul 2010 21:04:03 -0700 (PDT)
Date: Wed, 21 Jul 2010 23:04:09 -0500
From: Linda Dunbar <ldunbar@huawei.com>
In-reply-to: <000701cb28f4$ae1c90b0$0a55b210$@com>
To: 'Susan Hares' <skh@ndzh.com>, 'Brian E Carpenter' <brian.e.carpenter@gmail.com>, shares@ndzh.com
Message-id: <019f01cb2952$eff8d3f0$c6ec10ac@china.huawei.com>
MIME-version: 1.0
X-MIMEOLE: Produced By Microsoft MimeOLE V6.00.2900.3350
X-Mailer: Microsoft Office Outlook 11
Content-type: text/plain; charset="us-ascii"
Content-transfer-encoding: 7bit
Thread-index: AcsodPRKMfwh978LT7+/U4OMztZQ7QAfriUwABeYH4A=
References: <20100719221922.0DA383A6A7F@core3.amsl.com> <4C464ED1.1000601@gmail.com> <000701cb28f4$ae1c90b0$0a55b210$@com>
Cc: arp222@ietf.org
Subject: Re: [arp222] New Non-WG Mailing List: arp222@ietf.org
X-BeenThere: arp222@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: "Discussion of issues associated with large amount of virtual machines being introduced in data centers and virtual hosts introduced by Cloud Computing." <arp222.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/arp222>, <mailto:arp222-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/arp222>
List-Post: <mailto:arp222@ietf.org>
List-Help: <mailto:arp222-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/arp222>, <mailto:arp222-request@ietf.org?subject=subscribe>
X-List-Received-Date: Thu, 22 Jul 2010 04:03:48 -0000

IPv6 Neighbor Discovery protocol corresponds to a combination of the IPv4's
protocols: Address Resolution Protocol (ARP), ICMP Router Discovery, and
ICMP Redirect. ICMP Router Discovery might not be impacted by the large
amount of virtual hosts in Data Center and Cloud Computing. 

I will add those bullets in the slides so that people can debate which part
of IPv6 ND needs to be addressed. 

Linda Dunbar

-----Original Message-----
From: Susan Hares [mailto:skh@ndzh.com] 
Sent: Wednesday, July 21, 2010 11:49 AM
To: 'Brian E Carpenter'; ldunbar@huawei.com; shares@ndzh.com
Cc: arp222@ietf.org
Subject: RE: New Non-WG Mailing List: arp222@ietf.org

Brian:

This work is going beyond just ARP to a general solution for ND/RA/ ARP and
other Layer2 to Layer 2 information. 

In short, we are looking at trying to connect many areas of Layer 2 across
layer 3 infrastructure or many areas of Layer 2 across a L2 provider
network.  

We are first trying to define the problem to make sure we've included all
the things you mentioned: 

draft-dunbar-arp-for-large-dc-problem-statement-00.txt

Then, we believe we've got a generalized solution that will take care of
groups of ARP, DCHP, ND, RA, and future IPv6 additions. 

However, as all good IETF nerds do - we want to make sure we carefully
defined the problem. We'd appreciate your comments on the scope. We'd love
to hear if we've gotten the right scope for the problem. 

If you have 5 minutes at IETF, we can briefly go through the problems we
see. 

Best wishes, 

Sue Hares 


-----Original Message-----
From: Brian E Carpenter [mailto:brian.e.carpenter@gmail.com] 
Sent: Tuesday, July 20, 2010 9:35 PM
To: ldunbar@huawei.com; shares@ndzh.com
Cc: arp222@ietf.org
Subject: Re: New Non-WG Mailing List: arp222@ietf.org

I'm not going to join this list, no time, but I would be very
concerned if the work only considered ARP traffic. It's axiomatic
that you also have to consider Neighbor Discovery and Router Advertisement
traffic too. And if people start using IPv6's potential to create
virtual hosts by the million, the problem might be an order of magnitude
worse than ARP.

    Brian

On 2010-07-20 10:19, IESG Secretary wrote:
> A new IETF non-working group email list has been created.
> 
> List address: arp222@ietf.org
> Archive: http://www.ietf.org/mail-archive/web/arp222/
> To subscribe: https://www.ietf.org/mailman/listinfo/arp222
> 
> Description: This list discusses issues associated with large amount of
> virtual machines being introduced to data center. 
> 
> Virtual machines allow one physical server to support multiple hosts (20,
> 30, or hundreds of). As virtual machines are introduced to the Data Center
> (DC), the number of hosts within one subnet can grow dramatically.  This
> DC growth could tremendously impact to networks and hosts. Data Centers
> can span multiple subnets in a single site or multiple sites across a
> single AS or multiple ASes.
> 
> One issue is frequent ARP requests from hosts. All hosts send out
> frequent ARP requests due to their cache being aged out in minutes. With
> tens of thousands of hosts (each with a distinct MAC address) in one Data
> Center (DC), the amount of ARP packets per second is potentially in the
> 1,000 to 10,000/second.
> 
> For additional information, please contact the list administrators, Linda
> Dunbar and Sue Hares.
> _______________________________________________
> IETF-Announce mailing list
> IETF-Announce@ietf.org
> https://www.ietf.org/mailman/listinfo/ietf-announce
>